Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics

arXiv 2026 55.9 method, application

TLDR

Introduces NormWear-2, a world model for physiological signals using chaos-theoretic balancing and latent dynamics for multi-scale forecasting.

Reasoning

Strengths include novel chaos-theoretic balancing improving representation efficiency and evaluation on diverse real-world datasets with 8,026 subjects. Weaknesses: limited to physiological signals, no comparison to baselines or ablation studies mentioned in abstract.

Read-first score

Read-first score 55.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 37.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Citation impact 18%

79.3

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.7930392

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=dataset,evaluation,metric

Topical relevance 29%

52.9

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,dataset

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FoundationFrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 298.

Keyword Scores

world model

world dynamics prediction

generative world model

world simulator

interactive world model

model-based reinforcement learning world model

video world model

Deep Analysis

Innovations

Introduction of NormWear-2, a world model that encodes multivariate physiological signals and clinical intervention variables into a shared latent space and models their joint temporal evolution as a dynamical system.
Chaos-theoretic balancing of dynamical regime diversity during pretraining, which yields more robust representations and allows a smaller balanced corpus to outperform a larger unbalanced one.
Combination of inference from prior pre-trained knowledge (intuition) with instant non-parametric latent state transition adaptation (insight) for coherent multi-scale forecasting conditioned on heterogeneous clinical interventions.

Methodology

NormWear-2 encodes both multivariate physiological signals and clinical intervention variables into a shared latent space and models their joint temporal evolution as a dynamical system. The approach combines inference from prior pre-trained knowledge (intuition) with instant non-parametric latent state transition adaptation (insight). During pretraining, chaos-theoretic balancing of dynamical regime diversity is applied to improve representation robustness.

Key Results

NormWear-2 achieves the best overall forecasting performance across time, frequency, and latent representation domains, with significant improvements over state-of-the-art time series foundation models, while maintaining competitive downstream representation quality. A smaller balanced corpus outperforms one twice its size and captures bifurcation regimes.

Resources

Paper